AI Paper Atlas

Research map / Video / Video-language understanding

Efficient End-to-End Video Question Answering with Pyramidal Multimodal Transformer

Min Peng, Chongyang Wang, Yu Shi, Xiang-Dong Zhou

AAAI 2023 · Video › Video-language understanding · approach: Video-language pretraining · 9 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add the spatial-temporal decomposition to the pyramid (ablation)PMT · TGIF-QAAction accuracy: 85.4 -> 87.6Improved
Use contextual matching instead of up-sampling in the top-down pathway (ablation)PMT · TGIF-QAAction accuracy: 86.7 -> 87.6Improved
Use contextual matching instead of attention-based fusion in the top-down pathway (ablation)PMT · TGIF-QAAction accuracy: 86.5 -> 87.6Improved
Add the multistep loss constraint (ablation)PMT · TGIF-QAAction accuracy: 87.5 -> 87.6Improved
Replace default encoders with pre-trained TimeSformer and BERT (ablation)PMT · MSRVTT-QAaccuracy: +0.3Improved
Use 16 input frames rather than other tested frame counts (ablation)PMT · MSVD-QA and MSRVTT-QAaccuracyMixed
Set pyramid depth to L=3 instead of other tested depths (ablation)PMT · MSVD-QAaccuracyNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy